JP2022094342A - Place recommendation method, system, and program - Google Patents

Abstract

To provide a method, a system and a program for recommending information related to reservation information based on the reservation information.SOLUTION: The method of recommending a place includes the steps of: collecting reservation place information corresponding to a reservation event based on the reservation event performed on a user terminal; collecting related place information related to the reserved event based on search information searched on the user terminal; generating a sentence containing words corresponding to the reserved place information and the related place information, respectively; and embedding the words in the sentence.SELECTED DRAWING: Figure 2

Description

The present invention relates to methods, systems, and programs for recommending locations.

As technology develops, electronic devices (eg, smartphones, tablet PCs, etc.) are becoming more widespread, and thus Internet addiction is becoming more and more dependent on many parts of our daily lives.

With the development of various technologies including the Internet, the conventional consumption pattern that was highly dependent on offline (off-line) gradually moved to online (on-line), and now, online-centered consumption. Is increasing geometrically.

In addition, due to the characteristics of services such as the travel industry and the food industry, it is becoming common to attract customers through various online marketing even in industrial fields based on offline.

Along with such changes, in the offline-based industrial field, in order to improve user convenience, a reservation service via the Internet has been introduced. Therefore, customers, that is, users, can make reservations for various places such as accommodation facilities and restaurants by simply clicking an electronic device connected to the Internet several times.

As such a technique, Patent Document 1 discloses a general-purpose reservation method by service cooperation and a technique related to a system and a recording medium, and provides an online service reservation and payment process.

On the other hand, when a user makes a reservation for a specific place using an electronic device, the user shows an action pattern of finding food, play, fun, etc. by searching for a peripheral place related to the specific place.

Therefore, there is a need for a method of recommending various places related to a specific place, rather than simply providing a reservation service for the specific place to the user.

Korean Published Patent No. 10-2016-0105090

The present invention provides a place recommendation method, a system, and a program capable of recommending information related to the reservation information based on the reservation information.

More specifically, the present invention provides a place recommendation method, a system, and a program capable of recommending a meaningful related place to a user, centering on a reservation place corresponding to the reservation information.

The present invention also provides a place recommendation method, a system, and a program capable of recommending a related place suitable for the purpose of use of a user who uses the reserved place.

Further, the present invention provides a place recommendation method, a system, and a program capable of extracting meaningful related information based on the date information specified by the reservation information.

In order to solve the above problems, the place recommendation method according to the present invention includes a step of collecting reservation place information corresponding to the reservation event based on a reservation event performed on the user terminal, and a search on the user terminal. A step of collecting related place information related to the reserved place event and a step of generating a sentence including a word corresponding to the reserved place information and the related place information, respectively, based on the searched information. And, based on the step of embedding a word in the sentence and expressing the word contained in the sentence in the vector space and the distance between the words in the vector space, the vector. It may include a step of extracting recommended location information related to the reserved location information from the space.

Further, the place recommendation system according to the present invention includes a communication unit that communicates with a user terminal, a control unit that receives reservation location information corresponding to the reservation event based on a reservation event performed by the user terminal, and a control unit. including. The control unit receives the related place information related to the reserved event based on the search information searched by the user terminal, and sets the reserved place information and the word corresponding to the related place information, respectively. A sentence including a sentence (sentence) is generated, a word is embedding in the sentence, the word contained in the sentence is expressed in a vector space, and the distance between the words in the vector space is set. Based on this, the recommended place information related to the reserved place information can be extracted from the vector space.

Further, the program executed by one or more processes in the electronic device according to the present invention and can be stored in the computer-readable recording medium is the reservation place information corresponding to the reservation event based on the reservation event performed in the user terminal. A step of collecting related place information related to the reservation event based on the search information searched by the user terminal, and a word corresponding to the reserved place information and the related place information, respectively. A step of generating a sentence (sentence) including a word), a step of embedding a word in the sentence and expressing the word contained in the sentence on a vector space, and a step on the vector space. It may include a step of extracting recommended location information related to the reserved location information from the vector space based on the distance between the words and a command to execute.

As described above, the place recommendation method, the system, and the program according to the present invention collect related place information searched by the user terminal, centering on the reservation event generated by the user terminal, and make a reservation corresponding to the reservation event. It is possible to recommend location information that is related to location information.

At this time, in the present invention, by expressing the reserved place information and the related place information on the vector space based on the embedding of words, it is possible to extract the relevant information based on the reserved place information.

Further, the place recommendation method, system, and program according to the present invention secure information related to the reserved place information by collecting related information centering on the date when the reserved event occurs and the date corresponding to the reserved event. can do.

It is a conceptual diagram for demonstrating the place recommendation system by this invention. It is a flowchart for demonstrating the place recommendation method by this invention. It is a conceptual diagram for demonstrating the method of collecting reserved place information and related place information by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating the method of embedding a word about the place recommendation by this invention. It is a conceptual diagram for demonstrating utilization of place recommendation by this invention. It is a conceptual diagram for demonstrating utilization of place recommendation by this invention. It is a conceptual diagram for demonstrating utilization of place recommendation by this invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are designated by the same reference numerals regardless of the drawing numbers, and duplicate description thereof will be omitted. .. The component suffixes "module" and "part" used in the following description are added or mixed to facilitate the preparation of the specification, and are themselves significant or useful. I don't have it. Further, in explaining the embodiment of the present invention, if it is determined that the specific description of the related known technique makes the gist of the embodiment of the present invention unclear, the detailed description thereof will be omitted. Further, the accompanying drawings are merely to assist in understanding the embodiments of the present invention, and the accompanying drawings do not limit the technical idea of the present invention, and any modification included in the idea and the technical scope of the present invention. Should be understood to include, equivalents, or alternatives.

Terms including ordinal numbers, such as "first", "second", etc., are used to describe various components, but the components are not limited by the above terms. The above terms are used only to distinguish one component from the other.

When it is mentioned that one component is "connected" or "connected" to another component, it may be directly connected or connected to another component, with yet another component in the middle. It should be understood that it may exist. On the other hand, if it is mentioned that one component is "directly connected" or "directly connected" to another component, it should be understood that there is no other component in the middle. ..

The singular representation includes multiple representations unless otherwise noted.

As used herein, terms such as "including" and "having" seek to specify the existence of features, numbers, stages, actions, components, parts, or combinations thereof described herein. It should be understood that it does not preclude the existence or addability of one or more other features, numbers, stages, actions, components, components, or combinations thereof.

The present invention is for generating and providing useful information to the user and any third user based on the information collected from the user's terminal, and in particular, based on the reservation information. Regarding how to process data.

In the present invention, for convenience of explanation, the description will be centered on "reservation of place", but the present invention is not necessarily limited to this. That is, the "reservation" in the present invention includes not only the reservation of a place but also the reservation of services (including the reservation of services performed on the Internet), the reservation of food and drink provision, the reservation of participation in any event, and the like. Reservations are included.

The "place" in the present invention means a place where a certain thing is performed or occurs regardless of its type, and may be a place that is geographically, conceptually, or physically classified.

As an example, the "place" in the present invention may be a place for commercial purposes and may be a concept including a specific business establishment classified by a business establishment number or the like. In this case, the location may be accommodations (eg hotels, pensions, guest houses, condominiums, resorts, etc.), restaurants, theme parks, amusement facilities, beauty management salons (eg hair salons, nail salons, etc.), real estate agents. Includes establishments for specific commercial purposes, such as hospitals. In this case, the "reservation of a place" in the present invention is an accommodation reservation, a restaurant use reservation, or the like for using the business establishment.

For example, as shown in FIG. 1, a user makes a reservation for a place (for example, an accommodation facility called “Pension Yongli”) using a terminal 1000.

As another example, the "place" in the present invention can be a place for non-commercial purposes. In this case, the place includes a place that is operated non-profit for public or public interest purposes or for other purposes (eg, a museum, a building of a particular foundation, etc.). In this case, the "reservation of a place" in the present invention is a reservation for viewing a museum, a reservation for using a public facility, or the like for using the place.

As described above, in the present invention, the "place" includes various concepts, and the type and position of the "reserved place" is not limited as long as it can be reserved for use by the user.

Therefore, the "reservation place" in the present invention means a place that can be reserved by the reservation system accessible by the user's terminal. The user can access various reservation systems and make a reservation for a specific place through an application, a web browser, a program, software, etc. installed on the user's terminal.

In the present invention, the reservation system that provides reservation of a place is not particularly limited.

Further, the "related place" in the present invention means a place related to the reserved place, and means a place included in the information searched by the user's terminal.

Here, the searched information (or search information) means the information searched by a search service portal or the like that provides a search service.

Further, the searched information means specific information selected or clicked by the user among the search results of the search term input to the user's terminal.

In the above, it has been explained that the reservation of a place and the search for information are performed on the "user's terminal", which also means the user account (account). That is, the user's terminal means a terminal connected to or logged in to the user account.

Here, the user account means an account already registered in the place recommendation system according to the present invention. Such a user account means a user ID (identification, identification number).

As shown in FIG. 1, the present invention provides information 220 regarding a related place related to a reserved place (for example, an accommodation facility called “Pension Yongli”) (for example, a place located around the reserved place (restaurant, theme). Information about parks, etc.) About how to recommend a place to recommend. Hereinafter, along with the above-mentioned concept of a place, a place recommendation system and a method according to the present invention will be described more specifically. FIG. 1 is a conceptual diagram for explaining a place recommendation system according to the present invention.

First, as shown in FIG. 1, the user terminal (or user's terminal) 1000 means an electronic device. Here, the electronic device includes at least one of a smartphone, a mobile phone, a tablet PC, a kIOSK, a computer, a notebook computer, a digital broadcasting terminal, a PDA (Personal Digital Assistants), and a PMP (Portable Multimedia Player). include. Further, the user terminal 1000 may be an electronic device in which a user account is logged in, connected, or registered.

Hereinafter, duplicate description will be omitted for the user account logged in to the user terminal 1000. It goes without saying that the user terminal 1000 described below is an electronic device to which a user account is logged in, or an electronic device capable of collecting information by the location recommendation system 100 according to the present invention.

On the other hand, the place recommendation system 100 according to the present invention may include at least one of a communication unit 110, a storage unit 120, and a control unit 130.

The communication unit 110 can communicate with at least one of a user terminal 1000, an external storage (for example, a database (DB) 140), an external server, and a cloud server.

On the other hand, the external server or the cloud server may be configured to play at least a part of the control unit 130. That is, the execution of data processing, data calculation, and the like may be performed on an external server or a cloud server, and the method is not particularly limited in the present invention.

On the other hand, the communication unit 110 can support various communication methods in accordance with the communication standard of the communication target (for example, an electronic device, an external server, a device, etc.).

For example, the communication unit 110 includes WLAN (Wireless LAN), Wi-Fi (registered trademark) (Wireless Fidelity), Wi-Fi Direct (Wireless Fidelity Direct), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX. (World Interoperability for Microwave Access), HSDPA (High-Speed Downlink Packet Access), HSUPA (High-Speed Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), 5G (5th Generation) Mobile Telecommunication), Bluetooth® (Bluetooth), RFID (Radio Frequency Identification), IrDA (Infrared Data Association), UWB (Ultra Wide Band), ZigBee, NFC (Near Field Communication), and Wireless USB (Wireless Universal Serial) Bus) At least one of the technologies may be used to communicate with the communication target.

Next, the storage unit 120 may store various information according to the present invention. In the present invention, the storage unit 120 may be provided in the place recommendation system 100 itself. On the other hand, at least a part of the storage unit 120 may be at least one of the database (DB) 140 and the cloud storage (or cloud server). That is, it is understood that the storage unit 120 is sufficient as long as it is a space in which information necessary for the place recommendation system and method according to the present invention is stored, and there are no physical space restrictions. Therefore, in the following, the storage unit 120, the database 140, the external storage, and the cloud storage (or the cloud server) are not classified, and all of them are referred to as the storage unit 120.

The information stored in the storage unit 120 to provide the place recommendation method according to the present invention may include the reservation place information regarding the reservation place and the related place information regarding the related place.

First, "reservation place information" refers to information on a reservation place corresponding to a reservation event generated on a user terminal, and as described above, from information on various places (for example, accommodation facilities, restaurants, etc.). Become.

The "reservation event" in the present invention means a reservation of a specific place made by the user terminal, and is generated based on the user's selection.

The user can use the user terminal to perform a reservation process for using a specific place.

Reservations for such locations can be made on the reservation service page provided by the reservation system. The reservation system allows users to reserve locations on pages that they can connect to via the Internet (eg, web pages, application execution screens, etc.). Such reservation service pages may be provided together by the place recommendation system according to the present invention, or may be provided by another entity.

On the other hand, in the storage unit 120, not only the reservation place information but also the information about the reservation date (for example, the date, period, time, etc. using the reserved place) and the information about the reservation person (for example, the user) (for example, the user). At least one of (name, address, telephone number, user account (ID), payment method, payment date, etc.) may be further stored.

Next, the "related place information" refers to information related to the place related to the reservation event, and is the place searched by the user account logged in to the user terminal where the reservation event occurred or the user terminal where the reservation event occurred. Contains information about.

As described above, the searched information (or search information) means the information searched by the user terminal, and means the information searched by the search service portal or the like that provides the search service. Further, the searched information means specific information selected or clicked by the user among the search results of the search term input to the user terminal.

On the other hand, the reserved place information and the related place information may be matched and stored in the storage unit 120. Matching of this information may be performed based on the user terminal or the user account.

In the storage unit 120, the reservation place information regarding the reservation event generated by the same user account and the searched related place information may be matched and stored.

Next, the control unit 130 is configured to control the overall operation of the place recommendation system 100 according to the present invention. The control unit 130 can process signals, data, information and the like input or output by the above components, or provide or process appropriate information or functions to the user.

The control unit 130 includes at least one Central Processing Unit (CPU) and can execute the function according to the present invention. In addition, the control unit 130 can perform artificial intelligence-based data processing, and in particular, by embedding words, the place recommendation method according to the present invention can be executed. Further, the control unit 130 can execute the place recommendation method according to the present invention by at least one of machine learning and deep learning.

Hereinafter, the place recommendation method according to the present invention will be specifically described with reference to the attached drawings together with the above-described configuration.

FIG. 2 is a flowchart for explaining a place recommendation method according to the present invention, and FIG. 3 is a conceptual diagram for explaining a method for collecting reserved place information and related place information in the present invention. In addition, FIGS. 4, 5, 6, 7, 7, 8, and 10 are conceptual diagrams for explaining a method of embedding words for place recommendation in the present invention. Further, FIGS. 11, 12, and 13 are conceptual diagrams for explaining the utilization of the place recommendation in the present invention.

In the place recommendation method according to the present invention, as shown in FIG. 2, first, a process of collecting reservation place information corresponding to the reservation event is performed (S210).

When it is determined that the reservation event related to a specific place has occurred in the user terminal, the control unit 130 collects the reservation place information corresponding to the reservation event.

In FIG. 3A, a reservation event for a specific place (for example, “Jeju Guest House”) occurs in the user terminal 1000.

The control unit 130 includes not only the reservation place information but also information about the reservation date (for example, the reservation confirmation date, the reservation execution date, the date for using the reserved place, the period, the time, etc.) and the reservation person (for example, the user). Collect at least one of the information about (eg, name, address, phone number, user account (ID), payment method, payment date, etc.). The control unit 130 stores at least one of the collected reservation place information and the related information in the storage unit 120.

The reservation place information collected by the control unit 130 includes not only information about a specific user but also information about an unspecified number of users, and the control unit 130 is a reservation place corresponding to a wide variety of reservation events. Information can be collected.

Next, in the present invention, a process of collecting related place information related to the reserved event is performed (S220).

As described above, the related place information means the information related to the place related to the reservation event, and the place searched by the user account logged in to the user terminal where the reservation event occurred or the user terminal where the reservation event occurred. Contains information about.

Further, the searched information (or search information) means the information searched by the user terminal, and means the information searched by the search service portal or the like that provides the search service. Further, the searched information means specific information selected or clicked by the user among the search results of the search term input to the user terminal.

The control unit 130 collects at least a part of the information searched by the user terminal (or user account) in which the reservation event has occurred as related location information.

The control unit 130 may collect the searched information that satisfies the preset criteria as the related location information. That is, the related location information may be information that satisfies a preset condition.

Here, the preset conditions may relate to at least one of a date, a time point, and a period. For example, the control unit 130 can specify the location information included in the search information searched by the user terminal during a preset period related to the reservation event as the related location information.

That is, the control unit 130 can collect the location information included in the search information searched by the user terminal during the preset period related to the reservation event as the related location information. Relevant location information includes information about at least one location.

The preset period related to the reservation event is i) the specific date when the reservation event occurred, ii) the reservation date corresponding to the reservation event (date when the use of the reservation place was reserved), iii) the reservation event. Reservation period including the corresponding reservation date (for example, when one night or more is reserved), iv) Dates before and after the specific period based on the specific date when the reservation event occurred, v) Reservation corresponding to the reservation event It means at least one of the dates before and after within a specific period with respect to the date.

In the present invention, the place information included in the search information searched in the preset period is collected as the related place information in order to reflect the behavior pattern of the user. That is, the user searches for the date on which the reservation for the specific place is made, the date on which the specific place is actually used, and other places to be further used together with the specific place before and after those dates. Here, other places to be used further are places corresponding to food, play, fun things, and the like.

Therefore, for example, as shown in FIG. 3A, when the reservation event for a specific place occurs on a specific date (for example, October 30, 2020), the control unit 130 has FIG. 3B. And (c), at least one of the search information searched by the user terminal during the preset period satisfying the preset criteria based on the specific date (date when the reservation event occurred). Departments can be collected as related location information.

As an example, as shown in FIG. 3B, the control unit 130 has a specific period (for example, 3 days) based on a specific date (for example, October 30, 2020) when the reserved event occurs. At least a part of the search information searched by the user terminal on the dates before and after (for example, October 31, 2020) can be collected as related location information.

The control unit 130 collects the information searched by the user terminal, and from the searched information, the information searched (or the search) during a period satisfying a preset condition based on the date when the reservation event occurs. Location information included in the information provided) can be extracted. In addition, the extracted information can be specified as related location information.

With reference to the figure, the extracted information 320 is information about places such as Hyopche Ama's House 321, Hyopche Beach 322, and Hanlim Park 323.

As another example, as shown in FIGS. 3A and 3C, the control unit 130 includes a reservation period including a reservation date corresponding to the reservation event (for example, November 20, 2020, see reference numeral 311). (For example, when a reservation is made for one night or more) or at least a part of the search information searched by the user terminal before and after the period, 331, 332, 333, 334 can be collected as related place information.

The control unit 130 collects the information searched by the user terminal, and from the searched information, the reservation period including the reservation date corresponding to the reservation event or the information searched before or after the period (or the searched information). (Location information included in) can be extracted. In addition, the extracted information can be specified as related location information.

With reference to the figure, the extracted information 330 is information about places such as Songsan Hidemine 331, Hamdok Beach 332, Hyopche Beach 333, Camellia Hill 334, and the like.

In this way, when the information is searched by the user terminal, the control unit 130 collects the searched information and extracts (or selects) the related place information related to the reservation event from the collected information. Can be done.

On the other hand, the control unit 130, in order to extract information related to the reserved event, from the information searched on a specific date (or a specific period) based on the date related to the reserved event, the related place. Information can be extracted.

In the present invention, noise information that is not related location information related to the reservation event can be removed from the information searched by the user terminal, and the technique for removing the noise information is not particularly limited.

On the other hand, when the reserved place information and the related place information are extracted from the user terminal, the control unit 130 can match or associate the reserved place information with the related place information so as to satisfy at least one condition. ..

As an example, the control unit 130 may associate the reserved place information with the related place information in units of reserved events. In that case, the information associated with each other exists for each reserved event. That is, even if the reserved event has the same reserved place, if it is a different reservation, it is processed as different information. In that case, there are multiple datasets (or groups) corresponding to each reserved event.

Therefore, when a plurality of reserved events exist in the same reserved place, there are a plurality of data sets (or groups) including a plurality of reserved events or more, and related place information matching each of the same reserved places.

As another example, the control unit 130 may associate the reserved place information with the related place information in units of reserved places.

In that case, the control unit 130 associates all the related place information corresponding to the different reserved events with each other even if the reserved events are different, if the reserved places are the same.

In that case, even if there are a plurality of reserved events, if the reserved locations are all the same, there is a single data set (or group) containing related location information associated with each other based on the reserved locations.

Further, as another example, when a plurality of reserved events exist and all the reserved locations are the same, the control unit 130 divides the reserved locations into a plurality of data sets (or groups) according to a preset standard and associates them with the reserved location information. You may save it in association with the place information. In that case, the preset criteria are very different, such as the gender, age, residential area (or search area), reservation date, etc. of the user who made the reservation or searched for the information.

That is, the control unit 130 can group the reserved place information and the related place information by reflecting the characteristics of the user or the characteristics of the date.

In addition to the above example, the control unit 130 can store the reserved place information and the related place information in association with each other.

On the other hand, when the reserved place information and the related place information related to the reservation event are collected by at least one of the various methods described above, in the present invention, the sentence including the word corresponding to the reserved place information and the related place information, respectively. Is performed (S230).

As shown in FIG. 4, the control unit 130 combines the word 430 corresponding to the reserved place (for example, Jeju guest house) corresponding to the reserved place information 410 and the word 440 corresponding to the related place information 420, and is shown in FIG. As shown, sentence 510 can be generated.

As shown in the figure, when there are a plurality of related places, the control unit 130 has words 441, 442, 443, 444, 445 corresponding to the plurality of related places 421, 422, 423, 424, 425, respectively, and the reserved place information 410. The sentence 510 can be generated by using the word (word 1) 430 corresponding to the above. Referring to FIG. 5, in the generated sentence 510, the word 511 (511a, 511b, 511c) corresponding to the reserved place information 410 and the word 512, 513, 514, 515, 516 corresponding to the related place information 420, respectively, are included. And are included.

In the following, for convenience of explanation, the "word corresponding to the reserved place information" is referred to as a "reserved place word", and the "word corresponding to the related place information" is referred to as a "related place word".

In the present invention, the control unit 130 generates a sentence centering on the reserved place word, and the reserved place word is understood as a global context. When the control unit 130 generates a sentence based on the reservation event or the reservation place, the control unit 130 can globally input the reservation place word and generate the sentence.

For this purpose, as shown in FIG. 5, the control unit 130 arranges the reserved place words 511 (511a, 511b, 511c) between the plurality of related place words 512, 513, 514, 515, and 516, and sets the sentence 510. Can be generated. In that case, as shown in the figure, the reserved place word 511 (511a, 511b, 511c) is arranged a plurality of times in the generated sentence 510.

The control unit 130 can arrange the reserved place words 511 (511a, 511b, 511c) a plurality of times via at least one of the plurality of related place words 512, 513, 514, 515, and 516. As shown in the figure, at least one related place word is arranged between the reserved place words 511 (511a, 511b, 511c).

In addition, related place words may be placed multiple times in the generated sentence. When the search information corresponding to a specific related place word is searched a plurality of times by the user terminal 1000, the same related place word is arranged a plurality of times in the generated sentence.

On the other hand, how many times the reserved place word 511 (511a, 511b, 511c) is arranged in the generated sentence and how the arrangement interval is set are determined based on various criteria.

For example, the distance between the reserved place word and each of the plurality of related place words is determined based on the date when the search information corresponding to each of the plurality of related place words is searched and the date related to the reserved event.

The control unit 130 may give a weighted value to the related place word by adjusting the distance between the reserved place word and the related place word in consideration of the date when the search information corresponding to the related place word is searched. can.

Here, the distance between the reserved place word and each of the plurality of related place words may relate to how many other related place words are placed between the reserved place word and the specific related place word. The distance between words exists from 0 to n, depending on the number of related place words placed between them.

The control unit 130 determines how close the reserved place word is to the related place word and how many reserved place words are arranged in the vicinity according to the date when the search information corresponding to the related place word is searched. be able to.

For example, as shown in FIG. 7, the control unit 130 has a reservation date corresponding to the reservation event among a plurality of related place words 721, 722, 723, 724, 725, 726 (for example, November 20, 2020,). The word 726 (for example, Hamdoku beach) corresponding to the search information searched in (see FIG. 3) is arranged at a position close to the reserved place words 713 and 714 in the sentence.

As described above, in the present invention, a sentence can be generated using the reserved place word and the related place word, and the sentence to be embedded in the word can be secured.

In particular, the control unit 130 can impart a relationship between the reserved place word and the related place word by arranging the reserved place word a plurality of times in the sentence.

On the other hand, as shown in FIG. 5, the control unit 130 can generate various sentences 510, 520, and 530 centering on various reserved place words, and the number of sentences and the length of sentences can be determined according to the situation. It can be adjusted as appropriate.

As shown in FIG. 5, when different reserved events exist for different places, the control unit 130 can generate sentences 510, 520, and 530 corresponding to the different reserved events, respectively. As mentioned above, each of the sentences 510, 520, and 530 may relate to different reservation locations, or at least one may relate to the same reservation location.

Further, it goes without saying that the control unit 130 can generate different sentences for all of the reserved events when a reserved event related to a different reserved place or another reserved event related to the same place occurs on the same user terminal. ..

In the present invention, the reserved place word and the related place word are the names of places that can be identified by the user (or the names of business establishments, for example, Jeju Guest House, Hyopche), as shown in FIGS. 4, 5, and 7. It may consist of a ama's house, etc.). Further, in the present invention, the reserved place word and the related place word are information in a form in which the control unit 130 can process data as shown in FIG. 6, and each of them is registered in a preset database. It may consist of an ID (identification number) (or an ID of a business establishment) of a place corresponding to a word. That is, the words shown in the boxes shown in FIGS. 4, 5, and 7 are for explanation purposes, and the substantial data corresponding to the words is as shown in FIG. 6 (or a method similar thereto). It may be).

Referring to FIG. 6, in the sentence 610, the reserved place word (word 1) 611 (611a, 611b, 611c) is arranged a plurality of times. Further, in the sentence 610, at least one related place word (word 2, word 3) 612, 613 is included at least once.

As described above, when sentences related to reserved place information and related place information are generated, in the present invention, the process of embedding words in the generated sentences and converting the words contained in the sentences into vectors is performed. It is done (S240).

The control unit 130 can embed words in the generated sentence and express the words included in the sentence in the vector space as shown in FIGS. 8 and 9.

On the other hand, in step S230, generating a sentence together with the related place word by including the reserved place word a plurality of times is a relationship that the reserved place word and the related place word are related information when embedding the word. Corresponds to the work to give.

As shown in FIGS. 5 and 6, the control unit 130 can embed a word by using at least one sentence 510, 520, 530, 610, 620.

Word embedding is a method for Natural Language Processing (NLP) and is the most core technique of artificial intelligence to enable computers to understand and analyze human languages. Is.

By embedding such words, each word contained in a sentence can be represented by a vector, and such a vector is called a "word vector (or word vector)". A word represented by a vector has specific coordinates corresponding to the vector in the vector space. Therefore, the positions of words in the vector space are relatively close or distant depending on whether the words are similar or not.

The control unit 130 corresponds to each of the reserved place word and the related place word expressed on the vector space, which is derived based on the result of embedding the word in the sentence including the reserved place word and the related place word. The distance between the word vectors (or word vectors) to be used can be used to extract related place information related to the reserved place information.

The control unit 130 can embed words based on the POI (Point of Interest) 2vic algorithm. Further, the control unit 130 can embed words based on the word2vec algorithm.

The control unit 130 can embed a word that converts each of the reserved place word and the related place word into a vector based on the arrangement relationship between the reserved place word and the related place word in the sentence. Here, the dimensions of the vectors corresponding to the reserved place word and the related place word are defined in various ways.

Needless to say, the control unit 130 can embed words by using at least one of various algorithms that can derive the relationship between words included in the sentence, in addition to the algorithm. ..

As described above, after converting the word included in the sentence into a vector, in the present invention, the process of extracting the recommended place information related to the reserved place information is performed (S250).

Here, the reserved place information to be extracted of the recommended place information may be the reserved place information collected based on the reserved event in step S210, and the reserved place information specified by a different reserved event. May be.

That is, in the present invention, a database for extracting recommended place information is constructed by utilizing the reserved place information and related place information collected through various reservation events, and based on the database, useful information for various users. Can be provided. That is, the reserved place information to be extracted of the recommended place information may be the reserved place information corresponding to the reservation event of any user.

Therefore, it goes without saying that the reserved place information to be extracted from the recommended place information may be a place corresponding to the collected related place information.

On the other hand, the process of extracting recommended place information does not necessarily have to be performed continuously with the process of embedding words. That is, the control unit 130 can perform a process of extracting the recommended place information from the vector space when it is necessary to provide the recommended place information such as a user's request or the occurrence of a new reservation event.

In order to extract the recommended place information, the control unit 130 can perform a cosine similarity operation between the vectors expressed on the vector space.

The control unit 130 can perform a cosine similarity calculation between the reserved place word vector and the related place word vector corresponding to the reserved place word and the related place word, respectively.

That is, the control unit 130 can calculate the similarity between the reserved place word vector and the related place word vector by performing the cosine similarity calculation between the reserved place word vector and the related place word vector. The control unit 130 can perform a cosine similarity calculation between all the vectors converted by embedding the word or the vectors satisfying the preset conditions, centering on the reserved place word vector.

By such a cosine similarity operation, the reserved place word vector and the related place word vector are represented on the vector spaces 800 and 900 as shown in FIGS. 8 and 9.

The control unit 130 performs the cosine similarity calculation between the reserved place word vector and the related place word vector to obtain the reserved place word vector 810, 910 and the related place word vector 821, 822, 823, 824, 825, 827, 921, Relative distances between 922, 923, 924, 925 and 926 can be derived.

Further, the control unit 130 has at least one word vector 821, 822, 823, 824, 825, 921, 922, 923, 924 located within a preset distance 820, 920 from the reserved place word vectors 810, 910. 925 and 926 can be identified. The word vector specified in this way is a word vector corresponding to a place to be recommended, and is hereinafter referred to as a "recommended place word vector".

The control unit 130 can extract the place information corresponding to at least one of the recommended place word vectors 821, 822, 823, 824, 825, 921, 922, 923, 924, 925, 926 as the recommended place information. ..

In this way, the recommended place word vectors 821, 822, 823, 824, 825, 921, 922, 923, 924, 925, 926 located within the preset distance from the reserved place word vectors 810, 910 are reserved. It can be specified by the cosine similarity calculation between a plurality of word vectors included in the place word vectors 810 and 910 and the vector spaces 800 and 900.

The control unit 130 can extract as a recommended place a place corresponding to a preset number of word vectors arranged in the order of being close to the reserved place word vectors 810 and 910.

The control unit 130 can give a rank to the word vectors arranged in the order of being close to the reserved place word vectors 810 and 910. Further, the control unit 130 can extract a place corresponding to each recommended place word vector as a recommended place (or recommended place information) according to the order.

For example, as shown in FIG. 10A, based on the reserved place word vector, Cafe 1 1011, Cafe 2 1012, Theme Park 1 1013, Cafe 3 1014, Cafeteria 1 1015, Cafeteria 2 1016, Museum 1 1017, Recommended place information is extracted in the order of.

On the other hand, when the recommended place word vector located in the order of proximity to the reserved place word vector is extracted in this way, the recommended places corresponding to the extracted recommended place word vector may have low diversity. For example, when four places with high rankings are recommended among the recommended places, three places out of the four recommended places may be places corresponding to the same category (for example, "cafe").

Therefore, the control unit 130 may perform normalization of the recommended place information based on the category so that the recommended place information includes various places corresponding to different categories. Such normalization may be performed on all the word vectors contained in the vector space, or may be performed on the recommended place word vector specified as the recommended place information.

On the other hand, the control unit 130 specifies a preset number of recommended place word vectors located close to the reserved place word vector for each different category based on the reserved place word vector, and then the recommendation specified for each category. Recommended location information can be determined by normalizing between location word vectors.

That is, the control unit 130 can normalize the recommended place word vector so that the recommended place information includes the place information corresponding to different categories.

The control unit 130 can normalize the recommended place word vector by dividing the cosine similarity value of each recommended place word vector by log ₂ (1 + rank). Here, rank is information corresponding to the rank given by how close each recommended place word vector is to the reserved place word vector in the category including each recommended place word vector.

As a result of such normalization, the control unit 130 recommends place information corresponding to various categories such as cafes, theme parks, restaurants, museums, etc., as shown in FIG. 10 (b). It can be extracted as information.

As described above, in the place recommendation system and method according to the present invention, the place information useful to any user is recommended based on the similarity between the reserved place information and the related place information collected from various users. Can be done.

As an example of utilization of the place recommendation method according to the present invention, as shown in FIGS. 11A and 12A, when a reservation event for a specific place is generated by an arbitrary user, the control unit 130 causes a reservation event. Recommendation location information about can be recommended. The provision of such recommended place information may be performed based on the user's selections 1110 and 1210.

The control unit 130 identifies a word vector corresponding to the reservation place information (for example, "Pension Yongli") corresponding to the reservation event in the vector space constructed by the above method, and sets in advance from the specified word vector. The place information 1120 and 1220 corresponding to the word vector located within the specified distance can be provided to the user terminal 1000 as shown in FIG. 11 (b) and FIG. 12 (b).

As another utilization example, as shown in FIG. 13, when the search service page is requested to search for a specific search term on the user terminal, the control unit 130 vectorizes the location information related to the specific search term. It can be extracted from the space and provided as recommended location information. As shown in FIGS. 13 (a) and 13 (b), the control unit 130 is not only the information 1311, 1321 corresponding to the input specific search term, but also the user terminal (or the user terminal (or) to which the search request is made. User account) can further provide recommended location information 1322 for reserved events. At this time, the control unit 130 can provide the recommended place information 1322 regarding the reserved event only when the reserved place information corresponding to the reserved event is related to a specific search term. For example, as shown in FIG. 13 (b), the specific search term is a gourmet restaurant of "Jeju Island", and the reservation place information corresponding to the reservation event is the accommodation facility of "Jeju Island". The reservation place information corresponding to the above and the specific search term have a regional commonality of "Jeju Island".

As described above, when the information about the place included in the search term is related to the reservation place information corresponding to the reservation event, the control unit 130 is the user terminal or the user of the user account logged in to the user terminal. By providing the place related to the reservation place information corresponding to the reservation event as the recommended place information, it is possible to provide the user with useful information at various points in time.

As described above, the place recommendation method, the system, and the program according to the present invention collect related place information searched by the user terminal, centering on the reservation event generated by the user terminal, and make a reservation corresponding to the reservation event. It is possible to recommend location information that is related to location information.

At this time, in the present invention, by expressing the reserved place information and the related place information on the vector space based on the embedding of words, it is possible to extract the relevant information based on the reserved place information.

Further, the place recommendation method, system, and program according to the present invention secure information related to the reserved place information by collecting related information centering on the date when the reserved event occurs and the date corresponding to the reserved event. can do.

On the other hand, the above-mentioned invention can be realized as a program that is executed by one or more processes on a computer and can be stored in a computer-readable medium (or recording medium).

Further, the above-mentioned invention can be realized as a computer-readable code or a command on a program recording medium. That is, the present invention can be provided in the form of a program.

Computer-readable media, on the other hand, include all types of recording devices on which data readable by computer systems is recorded. Examples of computer-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SDD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy (registered trademark) disk, and optical data storage. Equipment, etc.

Further, the computer-readable medium may be a server or cloud storage that includes storage and can be accessed by electronic devices by communication. In this case, the computer can download the program according to the present invention from the server or cloud storage by wired or wireless communication.

Further, in the present invention, the computer described above is an electronic device equipped with a processor, that is, a central processing unit (CPU), and the type thereof is not particularly limited.

On the other hand, the detailed description of the present invention is exemplary and should not be construed as restrictive in all respects. The scope of the invention should be defined by a reasonable interpretation of the appended claims, and any modification within the equivalent scope of the invention is included in the scope of the invention.

110 Communication unit 120 Storage unit 130 Control unit 140 Database (DB)
1000 user terminal

Claims (10)

It ’s a place recommendation method.
A step of collecting reservation location information corresponding to the reservation event based on the reservation event generated on the user terminal, and
A step of collecting related location information related to the reservation event based on the search information searched by the user terminal, and
A step of generating a sentence containing a word corresponding to the reserved place information and the related place information, respectively.
A step of embedding a word in the sentence and expressing the word contained in the sentence in a vector space.
A step of extracting recommended place information related to the reserved place information from the vector space, and
A method characterized by including. The related location information includes a plurality of different related location information.
The step to generate the above sentence is
The sentence is generated by combining the reserved place word corresponding to the reserved place information and the plurality of related place words corresponding to the plurality of related place information, respectively.
The method according to claim 1. The step to generate the above sentence is
Including placing at least one reserved place word between the plurality of related place words to generate the sentence.
The method according to claim 2. In the above sentence
The distance between the reserved place word and the plurality of related place words is
The search information corresponding to each of the plurality of related place words is determined based on the date when the search information is searched and the date related to the reserved event.
The method according to claim 3. The step of collecting the relevant location information is
The present invention includes collecting the place information included in the search information searched by the user terminal during a preset period related to the reservation event as the related place information.
The method according to any one of claims 1 to 4. The step to generate the above sentence is
When a plurality of different reservation events occur on at least one terminal including the user terminal,
Generate multiple sentences corresponding to each of the above-mentioned multiple reservation events,
Words are embedded in the plurality of sentences, and the words included in each of the plurality of sentences are expressed in the vector space.
Including that
The method according to any one of claims 1 to 5. The step of extracting the recommended place information is
At least one recommended place word vector located within a preset distance from the reserved place word vector corresponding to the reserved place information is specified on the vector space.
Extracting the place information corresponding to at least one of the recommended place word vectors as the recommended place information.
including,
The method according to any one of claims 1 to 6. The step of extracting the recommended place information is
A step of normalizing the recommended location word vector so that the recommended location information includes location information corresponding to different categories.
7. The method of claim 7. The communication unit that communicates with the user terminal,
A control unit for receiving reservation location information corresponding to the reservation event based on the reservation event performed on the user terminal is included.
The control unit
Based on the search information searched by the user terminal, the related location information related to the reservation event is received, and the related location information is received.
Generate a sentence containing a word corresponding to the reserved place information and the related place information, respectively.
Words are embedded in the sentence, and the words contained in the sentence are expressed in the vector space.
Extracting recommended place information related to the reserved place information from the vector space,
A place recommendation system that features that. A step of collecting reservation location information corresponding to the reservation event based on the reservation event performed on the user terminal, and
A step of collecting related location information related to the reservation event based on the search information searched by the user terminal, and
A step of generating a sentence containing a word corresponding to the reserved place information and the related place information, respectively.
A step of embedding a word in the sentence and expressing the word contained in the sentence in a vector space.
A step of extracting recommended place information related to the reserved place information from the vector space, and
To execute,
A place recommendation program that features that.

Images